Merge branch 'development' of gitlab.lrz.de:dcdb/dcdb into development

analytics/README.md

@@ -855,6 +855,7 @@ The following are the configuration parameters available for the _Regressor_ plu
 | window | Length in milliseconds of the time window that is used to retrieve recent readings for the input sensors, starting from the latest one.
 | trainingSamples | Number of samples necessary to perform training of the current model.
 | targetDistance | Temporal distance (in terms of lags) of the sample that is to be predicted.
+| smoothResponses | If false, the regressor will attempt to predict one single sensor reading as specified by the _targetDistance_ parameter. If true, it will instead predict the _average_ of the upcoming _targetDistance_ sensor readings.
 | inputPath | Path of a file from which a pre-trained random forest model must be loaded.
 | outputPath | Path of a file to which the random forest model trained at runtime must be saved.
 | getImportances | If true, the random forest will also compute feature importance values when trained, which are printed.

analytics/operators/regressor/RegressorConfigurator.cpp

@@ -53,6 +53,8 @@ void RegressorConfigurator::operatorAttributes(RegressorOperator& op, CFG_VAL co
             op.setAggregationWindow(stoull(val.second.data()) * 1000000);
         else if(boost::iequals(val.first, "targetDistance"))
             op.setTargetDistance(stoull(val.second.data()));
+        else if(boost::iequals(val.first, "smoothResponses"))
+            op.setSmoothResponses(to_bool(val.second.data()));
         else if(boost::iequals(val.first, "inputPath"))
             op.setInputPath(val.second.data());
         else if(boost::iequals(val.first, "outputPath"))

analytics/operators/regressor/RegressorOperator.cpp

@@ -32,6 +32,7 @@ RegressorOperator::RegressorOperator(const std::string& name) : OperatorTemplate
     _modelOut = "";
     _aggregationWindow = 0;
     _targetDistance = 1;
+    _smoothResponses = false;
     _numFeatures = REG_NUMFEATURES;
     _trainingSamples = 256;
     _trainingPending = true;
@@ -47,6 +48,7 @@ RegressorOperator::RegressorOperator(const RegressorOperator& other) : OperatorT
     _modelOut = "";
     _aggregationWindow = other._aggregationWindow;
     _targetDistance = other._targetDistance;
+    _smoothResponses = other._smoothResponses;
     _numFeatures = other._numFeatures;
     _trainingSamples = other._trainingSamples;
     _importances = other._importances;
@@ -105,6 +107,7 @@ void RegressorOperator::execOnInit() {
 void RegressorOperator::printConfig(LOG_LEVEL ll) {
     LOG_VAR(ll) << "            Window:          " << _aggregationWindow;
     LOG_VAR(ll) << "            Target Distance: " << _targetDistance;
+    LOG_VAR(ll) << "            Smooth Response: " << (_smoothResponses ? "enabled" : "disabled");
     LOG_VAR(ll) << "            Training Sample: " << _trainingSamples;
     LOG_VAR(ll) << "            Input Path:      " << (_modelIn!="" ? _modelIn : std::string("none"));
     LOG_VAR(ll) << "            Output Path:     " << (_modelOut!="" ? _modelOut : std::string("none"));
@@ -143,10 +146,15 @@ void RegressorOperator::trainRandomForest(bool categorical) {
     if((uint64_t)_responseSet->size().height <= _targetDistance)
         throw std::runtime_error("Operator " + _name + ": cannot perform training, insufficient data!");
     // Shifting the training and response sets so as to obtain the desired prediction distance
-    *_responseSet = _responseSet->rowRange(_targetDistance, _responseSet->size().height);
+    if(!categorical && _smoothResponses && _targetDistance>0) {
+        smoothResponsesArray();
+        *_responseSet = _responseSet->rowRange(0, _responseSet->size().height-_targetDistance);
+    } else {
+        *_responseSet = _responseSet->rowRange(_targetDistance, _responseSet->size().height);
+    }
     *_trainingSet = _trainingSet->rowRange(0, _trainingSet->size().height-_targetDistance);
     shuffleTrainingSet();
-
+    
     cv::Mat varType = cv::Mat(_trainingSet->size().width + 1, 1, CV_8U);
     varType.setTo(cv::Scalar(cv::ml::VAR_NUMERICAL));
     varType.at<unsigned char>(_trainingSet->size().width, 0) = categorical ? cv::ml::VAR_CATEGORICAL : cv::ml::VAR_NUMERICAL;
@@ -171,6 +179,16 @@ void RegressorOperator::trainRandomForest(bool categorical) {
     }
 }
 
+void RegressorOperator::smoothResponsesArray() {
+    for(size_t midx=0; midx < (_responseSet->size().height - _targetDistance); midx++) {
+        float meanBuf = 0;
+        for(size_t nidx=0; nidx <= _targetDistance; nidx++) {
+            meanBuf += _responseSet->at<float>(midx + nidx);
+        }
+        _responseSet->at<float>(midx) = meanBuf / (_targetDistance + 1);
+    }
+}
+
 void RegressorOperator::shuffleTrainingSet() {
     if(!_trainingSet || !_responseSet)
         return;

analytics/operators/regressor/RegressorOperator.h

@@ -65,6 +65,7 @@ public:
     void setComputeImportances(bool i)                   { _importances = i; }
     void setRawMode(bool r)                              { _numFeatures = r ? 1 : REG_NUMFEATURES; }
     void triggerTraining()                               { _trainingPending = true;}
+    void setSmoothResponses(bool s)                      { _smoothResponses = s; }
 
     std::string getInputPath()                           { return _modelIn;}
     std::string getOutputPath()                          { return _modelOut; }
@@ -72,6 +73,7 @@ public:
     unsigned long long getTrainingSamples()              { return _trainingSamples; }
     bool getComputeImportances()                         { return _importances; }
     bool getRawMode()                                    { return _numFeatures != REG_NUMFEATURES; }
+    bool getSmoothResponses()                            { return _smoothResponses; }
 
     virtual void printConfig(LOG_LEVEL ll) override;
 
@@ -81,6 +83,7 @@ protected:
     bool computeFeatureVector(U_Ptr unit);
     void trainRandomForest(bool categorical=false);
     void shuffleTrainingSet();
+    void smoothResponsesArray();
     std::string getImportances();
     
     std::string _modelOut;
@@ -89,6 +92,7 @@ protected:
     unsigned long long _trainingSamples;
     unsigned long long _targetDistance;
     unsigned long long _numFeatures;
+    bool _smoothResponses;
     bool _trainingPending;
     bool _importances;
     bool _includeTarget;